Triple

T22198707
Position Surface form Disambiguated ID Type / Status
Subject Conrad de Rosen E548616 entity
Predicate familyName P18 FINISHED
Object de Rosen NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: de Rosen | Statement: [Conrad de Rosen, familyName, de Rosen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: de Rosen
Context triple: [Conrad de Rosen, familyName, de Rosen]
  • A. de Berghes
    de Berghes is a noble family name of likely Belgian or Dutch origin historically associated with aristocratic lineages in the Low Countries.
  • B. Roeser
    Roeser is a commune and small town in southern Luxembourg, situated just south of Luxembourg City in the country’s Minett region.
  • C. de Ross
    De Ross is a variant form of the surname Ross, typically associated with families of Scottish or Norman origin.
  • D. von Rosen chosen
    von Rosen is a Swedish noble family name historically associated with aristocratic lineage and cultural figures in Sweden.
  • E. Roussel
    Roussel is a surname of French origin, often used as an alternative spelling of Russell.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e11e3ecc7c8190b5f94cd8f42e9d37 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12ae98808819081582a57bca6312b completed April 28, 2026, 9:47 p.m.
Created at: April 16, 2026, 8:36 p.m.